walker2d-v1-ppo:
    env: Walker2d-v1
    run: PPO
    config:
        kl_coeff: 1.0
        num_sgd_iter: 20
        lr: .0001
        sgd_minibatch_size: 32768
        train_batch_size: 320000
        num_workers: 64
        num_gpus: 4
        batch_mode: complete_episodes
        observation_filter: MeanStdFilter